在该项目中,你将使用生成式对抗网络(Generative Adversarial Nets)来生成新的人脸图像。
该项目将使用以下数据集:
由于 CelebA 数据集比较复杂,而且这是你第一次使用 GANs。我们想让你先在 MNIST 数据集上测试你的 GANs 模型,以让你更快的评估所建立模型的性能。
如果你在使用 FloydHub, 请将 data_dir 设置为 "/input" 并使用 FloydHub data ID "R5KrjnANiKVhLWAkpXhNBe".
data_dir = './data'
# FloydHub - Use with data ID "R5KrjnANiKVhLWAkpXhNBe"
#data_dir = '/input'
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import helper
helper.download_extract('mnist', data_dir)
helper.download_extract('celeba', data_dir)
show_n_images = 25
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
%matplotlib inline
import os
from glob import glob
from matplotlib import pyplot
mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'mnist/*.jpg'))[:show_n_images], 28, 28, 'L')
pyplot.imshow(helper.images_square_grid(mnist_images, 'L'), cmap='gray')
CelebFaces Attributes Dataset (CelebA) 是一个包含 20 多万张名人图片及相关图片说明的数据集。你将用此数据集生成人脸,不会用不到相关说明。你可以更改 show_n_images 探索此数据集。
show_n_images = 25
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'img_align_celeba/*.jpg'))[:show_n_images], 28, 28, 'RGB')
pyplot.imshow(helper.images_square_grid(mnist_images, 'RGB'))
由于该项目的重点是建立 GANs 模型,我们将为你预处理数据。
经过数据预处理,MNIST 和 CelebA 数据集的值在 28×28 维度图像的 [-0.5, 0.5] 范围内。CelebA 数据集中的图像裁剪了非脸部的图像部分,然后调整到 28x28 维度。
MNIST 数据集中的图像是单通道的黑白图像,CelebA 数据集中的图像是 三通道的 RGB 彩色图像。
你将通过部署以下函数来建立 GANs 的主要组成部分:
model_inputsdiscriminatorgeneratormodel_lossmodel_opttrain检查你是否使用正确的 TensorFlow 版本,并获取 GPU 型号
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
from distutils.version import LooseVersion
import warnings
import tensorflow as tf
# Check TensorFlow Version
assert LooseVersion(tf.__version__) >= LooseVersion('1.0'), 'Please use TensorFlow version 1.0 or newer. You are using {}'.format(tf.__version__)
print('TensorFlow Version: {}'.format(tf.__version__))
# Check for a GPU
if not tf.test.gpu_device_name():
warnings.warn('No GPU found. Please use a GPU to train your neural network.')
else:
print('Default GPU Device: {}'.format(tf.test.gpu_device_name()))
部署 model_inputs 函数以创建用于神经网络的 占位符 (TF Placeholders)。请创建以下占位符:
image_width,image_height 和 image_channels 设置为 rank 4。z_dim。返回占位符元组的形状为 (tensor of real input images, tensor of z data, learning rate)。
import problem_unittests as tests
def model_inputs(image_width, image_height, image_channels, z_dim):
"""
Create the model inputs
:param image_width: The input image width
:param image_height: The input image height
:param image_channels: The number of image channels
:param z_dim: The dimension of Z
:return: Tuple of (tensor of real input images, tensor of z data, learning rate)
"""
# TODO: Implement Function
inputs = tf.placeholder(tf.float32, (None, image_width, image_height, image_channels), name='input')
input_z = tf.placeholder(tf.float32, (None, z_dim), name='z_dim')
lr = tf.placeholder(tf.float32)
return inputs, input_z, lr
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_inputs(model_inputs)
部署 discriminator 函数创建辨别器神经网络以辨别 images。该函数应能够重复使用神经网络中的各种变量。 在 tf.variable_scope 中使用 "discriminator" 的变量空间名来重复使用该函数中的变量。
该函数应返回形如 (tensor output of the discriminator, tensor logits of the discriminator) 的元组。
def discriminator(images, reuse=False):
"""
Create the discriminator network
:param image: Tensor of input image(s)
:param reuse: Boolean if the weights should be reused
:return: Tuple of (tensor output of the discriminator, tensor logits of the discriminator)
"""
alpha = 0.2
with tf.variable_scope('discriminator', reuse=reuse):
# images is 28x28x?
x1 = tf.layers.conv2d(images, 64, 5, strides=2, padding='same')
x1 = tf.maximum(x1 * alpha, x1)
# 14x14x64
x2 = tf.layers.conv2d(x1, 128, 5, strides=2, padding='same')
x2 = tf.layers.batch_normalization(x2, training=True)
x2 = tf.maximum(x2* alpha, x2)
# 7x7x128
x3 = tf.layers.conv2d(x1, 256, 5, strides=2, padding='same')
x3 = tf.layers.batch_normalization(x3, training=True)
x3 = tf.maximum(x3* alpha, x3)
# ?x?x256
# Flatten
x4 = tf.reshape(x3, (-1, 4*4*256))
logits = tf.layers.dense(x4, 1)
out = tf.nn.sigmoid(logits)
return out, logits
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_discriminator(discriminator, tf)
部署 generator 函数以使用 z 生成图像。该函数应能够重复使用神经网络中的各种变量。
在 tf.variable_scope 中使用 "generator" 的变量空间名来重复使用该函数中的变量。
该函数应返回所生成的 28 x 28 x out_channel_dim 维度图像。
def generator(z, out_channel_dim, is_train=True):
"""
Create the generator network
:param z: Input z
:param out_channel_dim: The number of channels in the output image
:param is_train: Boolean if generator is being used for training
:return: The tensor output of the generator
"""
alpha = 0.2
with tf.variable_scope('generator', reuse=not is_train):
# z to 4x4x512
x1 = tf.layers.dense(z, 2*2*512)
# reshape
x1 = tf.reshape(x1, (-1,2,2,512))
x1 = tf.layers.batch_normalization(x1, training=is_train)
x1 = tf.maximum(alpha * x1, x1)
# now 3x3x512
x2 = tf.layers.conv2d_transpose(x1, 256, 5, strides=2, padding='valid')
x2 = tf.layers.batch_normalization(x2, training=is_train)
x2 = tf.maximum(alpha * x2, x2)
# now 7x7x256
x3 = tf.layers.conv2d_transpose(x2, 128, 5, strides=2, padding='same')
x3 = tf.layers.batch_normalization(x3, training=is_train)
x3 = tf.maximum(alpha * x3, x3)
# now 14x14x128
logits = tf.layers.conv2d_transpose(x3, out_channel_dim, 5, strides=2, padding='same')
# now 28x28x?
out = tf.tanh(logits)
return out
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_generator(generator, tf)
部署 model_loss 函数训练并计算 GANs 的损失。该函数应返回形如 (discriminator loss, generator loss) 的元组。
使用你已实现的函数:
discriminator(images, reuse=False)generator(z, out_channel_dim, is_train=True)def model_loss(input_real, input_z, out_channel_dim):
"""
Get the loss for the discriminator and generator
:param input_real: Images from the real dataset
:param input_z: Z input
:param out_channel_dim: The number of channels in the output image
:return: A tuple of (discriminator loss, generator loss)
"""
model_fake = generator(input_z, out_channel_dim, is_train=True)
real_out, real_logits = discriminator(input_real)
fake_out, fake_logits = discriminator(model_fake, reuse=True)
d_loss_real = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(
logits=real_logits, labels=tf.ones_like(real_out)))
d_loss_fake = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(
logits=fake_logits, labels=tf.zeros_like(fake_out)))
d_loss = d_loss_real + d_loss_fake
g_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(
logits=fake_logits, labels=tf.ones_like(fake_out)))
return d_loss, g_loss
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_loss(model_loss)
部署 model_opt 函数实现对 GANs 的优化。使用 tf.trainable_variables 获取可训练的所有变量。通过变量空间名 discriminator 和 generator 来过滤变量。该函数应返回形如 (discriminator training operation, generator training operation) 的元组。
def model_opt(d_loss, g_loss, learning_rate, beta1):
"""
Get optimization operations
:param d_loss: Discriminator loss Tensor
:param g_loss: Generator loss Tensor
:param learning_rate: Learning Rate Placeholder
:param beta1: The exponential decay rate for the 1st moment in the optimizer
:return: A tuple of (discriminator training operation, generator training operation)
"""
t_vars = tf.trainable_variables()
g_vars = [var for var in t_vars if var.name.startswith('generator')]
d_vars = [var for var in t_vars if var.name.startswith('discriminator')]
with tf.control_dependencies(tf.get_collection(tf.GraphKeys.UPDATE_OPS)):
d_opt = tf.train.AdamOptimizer(learning_rate=learning_rate, beta1=beta1).minimize(d_loss, var_list=d_vars)
g_opt = tf.train.AdamOptimizer(learning_rate=learning_rate, beta1=beta1).minimize(g_loss, var_list=g_vars)
return d_opt, g_opt
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_opt(model_opt, tf)
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import numpy as np
def show_generator_output(sess, n_images, input_z, out_channel_dim, image_mode):
"""
Show example output for the generator
:param sess: TensorFlow session
:param n_images: Number of Images to display
:param input_z: Input Z Tensor
:param out_channel_dim: The number of channels in the output image
:param image_mode: The mode to use for images ("RGB" or "L")
"""
cmap = None if image_mode == 'RGB' else 'gray'
z_dim = input_z.get_shape().as_list()[-1]
example_z = np.random.uniform(-1, 1, size=[n_images, z_dim])
samples = sess.run(
generator(input_z, out_channel_dim, False),
feed_dict={input_z: example_z})
images_grid = helper.images_square_grid(samples, image_mode)
pyplot.imshow(images_grid, cmap=cmap)
pyplot.show()
部署 train 函数以建立并训练 GANs 模型。记得使用以下你已完成的函数:
model_inputs(image_width, image_height, image_channels, z_dim)model_loss(input_real, input_z, out_channel_dim)model_opt(d_loss, g_loss, learning_rate, beta1)使用 show_generator_output 函数显示 generator 在训练过程中的输出。
注意:在每个批次 (batch) 中运行 show_generator_output 函数会显著增加训练时间与该 notebook 的体积。推荐每 100 批次输出一次 generator 的输出。
def train(epoch_count, batch_size, z_dim, learning_rate, beta1, get_batches, data_shape, data_image_mode):
"""
Train the GAN
:param epoch_count: Number of epochs
:param batch_size: Batch Size
:param z_dim: Z dimension
:param learning_rate: Learning Rate
:param beta1: The exponential decay rate for the 1st moment in the optimizer
:param get_batches: Function to get batches
:param data_shape: Shape of the data
:param data_image_mode: The image mode to use for images ("RGB" or "L")
"""
# TODO: Build Model
_, img_width, img_height, img_channels = data_shape
inputs, input_z, lr = model_inputs(img_width, img_height, img_channels, z_dim)
d_loss, g_loss = model_loss(inputs, input_z, img_channels)
d_opt, g_opt = model_opt(d_loss, g_loss, lr, beta1)
print_every = 5
show_every = 100
show_n_images = 25
steps = 0
print_head = False
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch_i in range(epoch_count):
for batch_images in get_batches(batch_size):
# TODO: Train Model
steps+=1
batch_images*=2
batch_z = np.random.uniform(-1, 1, size=(batch_size, z_dim))
_ = sess.run(d_opt, feed_dict={inputs: batch_images, input_z: batch_z, lr: learning_rate})
_ = sess.run(g_opt, feed_dict={inputs: batch_images, input_z: batch_z, lr: learning_rate})
if steps % print_every == 0:
if not print_head:
print("Epoch {}/{} S(D,G) ".format(epoch_i, epoch_count), end='')
print_head = True
d_loss_val = d_loss.eval({input_z: batch_z, inputs: batch_images})
g_loss_val = g_loss.eval({input_z: batch_z})
print("{}({:.4f} {:.4f}) ".format(steps, d_loss_val, g_loss_val), end='')
if steps % show_every == 0:
print('')
print_head = False
show_generator_output(sess, show_n_images, input_z, img_channels, data_image_mode)
print("\nDone!")
show_generator_output(sess, show_n_images, input_z, img_channels, data_image_mode)
在 MNIST 上测试你的 GANs 模型。经过 2 次迭代,GANs 应该能够生成类似手写数字的图像。确保生成器 (generator) 低于辨别器 (discriminator) 的损失,或接近 0。
batch_size = 64
z_dim = 100
learning_rate = 0.003
beta1 = 0.5
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
epochs = 2
mnist_dataset = helper.Dataset('mnist', glob(os.path.join(data_dir, 'mnist/*.jpg')))
with tf.Graph().as_default():
train(epochs, batch_size, z_dim, learning_rate, beta1, mnist_dataset.get_batches,
mnist_dataset.shape, mnist_dataset.image_mode)
在 CelebA 上运行你的 GANs 模型。在一般的GPU上运行每次迭代大约需要 20 分钟。你可以运行整个迭代,或者当 GANs 开始产生真实人脸图像时停止它。
batch_size = 64
z_dim = 200
learning_rate = 0.001
beta1 = 0.5
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
epochs = 5
celeba_dataset = helper.Dataset('celeba', glob(os.path.join(data_dir, 'img_align_celeba/*.jpg')))
with tf.Graph().as_default():
train(epochs, batch_size, z_dim, learning_rate, beta1, celeba_dataset.get_batches,
celeba_dataset.shape, celeba_dataset.image_mode)
提交本项目前,确保运行所有 cells 后保存该文件。
保存该文件为 "dlnd_face_generation.ipynb", 并另存为 HTML 格式 "File" -> "Download as"。提交项目时请附带 "helper.py" 和 "problem_unittests.py" 文件。